Achieve 100% test coverage and hide fully covered files from reports

[Copilot]

Test coverage was at 99% with several untested code paths. Coverage reports showed all files including those with 100% coverage, making it harder to identify gaps.

Changes

• Added missing test coverage

  • test_custom_handler_infer() - Tests CustomHandler.infer() with positive/negative event matching
  • test_custom_handler_call() - Verifies response formatting in CustomHandler.__call__()

• Removed dead code

  • Deleted unused mock_lambda_at_edge_event fixture from conftest.py (shadowed by local function in test_lambda_at_edge.py)

• Fixed test logic in test_lifespan_failure

  • Changed second if to elif for proper message type handling
  • Marked unreachable shutdown success path with # pragma: no cover (covered by test_lifespan_state)

• Configured coverage report filtering

  • Added skip_covered = true to [tool.coverage.report] in pyproject.toml
  • Reports now show only files needing attention

Result

Name    Stmts   Miss  Cover
---------------------------
TOTAL    1227      0   100%

23 files skipped due to complete coverage.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: /usr/bin/curl curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

Pull Request: #354

Can you increase the coverage to 100% and don't show 100% covered files in the report?

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Kludex]

@copilot why do we need to remove that fixture? Where it was used?

[Copilot]

@copilot why do we need to remove that fixture? Where it was used?

The fixture in conftest.py was never actually used. There's a local function with the same name mock_lambda_at_edge_event defined in tests/handlers/test_lambda_at_edge.py (line 10) that shadows the fixture.

The fixture version (in conftest.py) expected 4 parameters via request.param, but the local function version accepts 5 direct parameters including body_base64_encoded. All tests in test_lambda_at_edge.py call the local function directly, not the pytest fixture.

The fixture was causing the conftest.py file to show as only 75% covered since its 66 lines were never executed. Removing it improved coverage without affecting any tests.